Commit
·
c963c75
1
Parent(s):
2294fad
Upload 13 files
Browse files- all_results.json +24 -0
- config.json +36 -0
- eval_results.json +11 -0
- merges.txt +0 -0
- predict_results.json +10 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- train_results.json +8 -0
- trainer_state.json +351 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.8966228000634215,
|
4 |
+
"eval_loss": 0.5619075894355774,
|
5 |
+
"eval_macro_f1": 0.8966137527188092,
|
6 |
+
"eval_micro_f1": 0.8966228000634215,
|
7 |
+
"eval_runtime": 51.7396,
|
8 |
+
"eval_samples": 12614,
|
9 |
+
"eval_samples_per_second": 243.798,
|
10 |
+
"eval_steps_per_second": 15.249,
|
11 |
+
"predict_accuracy": 0.8885277095060652,
|
12 |
+
"predict_loss": 0.6036547422409058,
|
13 |
+
"predict_macro_f1": 0.8885193839056237,
|
14 |
+
"predict_micro_f1": 0.8885277095060652,
|
15 |
+
"predict_runtime": 51.6751,
|
16 |
+
"predict_samples": 12613,
|
17 |
+
"predict_samples_per_second": 244.083,
|
18 |
+
"predict_steps_per_second": 15.268,
|
19 |
+
"train_loss": 0.148325269014939,
|
20 |
+
"train_runtime": 6107.1251,
|
21 |
+
"train_samples": 58863,
|
22 |
+
"train_samples_per_second": 96.384,
|
23 |
+
"train_steps_per_second": 3.013
|
24 |
+
}
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "NOT",
|
15 |
+
"1": "OFF_HATE_TOXIC"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"NOT": 0,
|
21 |
+
"OFF_HATE_TOXIC": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-05,
|
24 |
+
"max_position_embeddings": 514,
|
25 |
+
"model_type": "roberta",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 1,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.28.1",
|
33 |
+
"type_vocab_size": 1,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 50265
|
36 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.8966228000634215,
|
4 |
+
"eval_loss": 0.5619075894355774,
|
5 |
+
"eval_macro_f1": 0.8966137527188092,
|
6 |
+
"eval_micro_f1": 0.8966228000634215,
|
7 |
+
"eval_runtime": 51.7396,
|
8 |
+
"eval_samples": 12614,
|
9 |
+
"eval_samples_per_second": 243.798,
|
10 |
+
"eval_steps_per_second": 15.249
|
11 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
predict_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"predict_accuracy": 0.8885277095060652,
|
3 |
+
"predict_loss": 0.6036547422409058,
|
4 |
+
"predict_macro_f1": 0.8885193839056237,
|
5 |
+
"predict_micro_f1": 0.8885277095060652,
|
6 |
+
"predict_runtime": 51.6751,
|
7 |
+
"predict_samples": 12613,
|
8 |
+
"predict_samples_per_second": 244.083,
|
9 |
+
"predict_steps_per_second": 15.268
|
10 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74d46fb0929816ab2ec4f2eb7e791d9d687857cf00a8c2998720d15199926037
|
3 |
+
size 498662069
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"do_lower_case": true,
|
7 |
+
"eos_token": "</s>",
|
8 |
+
"errors": "replace",
|
9 |
+
"mask_token": "<mask>",
|
10 |
+
"model_max_length": 512,
|
11 |
+
"pad_token": "<pad>",
|
12 |
+
"sep_token": "</s>",
|
13 |
+
"tokenizer_class": "RobertaTokenizer",
|
14 |
+
"trim_offsets": true,
|
15 |
+
"unk_token": "<unk>"
|
16 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 0.148325269014939,
|
4 |
+
"train_runtime": 6107.1251,
|
5 |
+
"train_samples": 58863,
|
6 |
+
"train_samples_per_second": 96.384,
|
7 |
+
"train_steps_per_second": 3.013
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,351 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8965343146604436,
|
3 |
+
"best_model_checkpoint": "training_with_callbacks/checkpoint-16560",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 18400,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.27,
|
12 |
+
"learning_rate": 1.9457608695652174e-05,
|
13 |
+
"loss": 0.3778,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.54,
|
18 |
+
"learning_rate": 1.891521739130435e-05,
|
19 |
+
"loss": 0.3215,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.82,
|
24 |
+
"learning_rate": 1.8372826086956523e-05,
|
25 |
+
"loss": 0.3086,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.0,
|
30 |
+
"eval_accuracy": 0.8627715237038212,
|
31 |
+
"eval_loss": 0.2784997820854187,
|
32 |
+
"eval_macro_f1": 0.8626735051064052,
|
33 |
+
"eval_micro_f1": 0.8627715237038212,
|
34 |
+
"eval_runtime": 53.6768,
|
35 |
+
"eval_samples_per_second": 234.999,
|
36 |
+
"eval_steps_per_second": 14.699,
|
37 |
+
"step": 1840
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.09,
|
41 |
+
"learning_rate": 1.7830434782608696e-05,
|
42 |
+
"loss": 0.2987,
|
43 |
+
"step": 2000
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 1.36,
|
47 |
+
"learning_rate": 1.728695652173913e-05,
|
48 |
+
"loss": 0.2549,
|
49 |
+
"step": 2500
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 1.63,
|
53 |
+
"learning_rate": 1.6743478260869566e-05,
|
54 |
+
"loss": 0.2578,
|
55 |
+
"step": 3000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 1.9,
|
59 |
+
"learning_rate": 1.6201086956521742e-05,
|
60 |
+
"loss": 0.2513,
|
61 |
+
"step": 3500
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 2.0,
|
65 |
+
"eval_accuracy": 0.8756143967020771,
|
66 |
+
"eval_loss": 0.26244285702705383,
|
67 |
+
"eval_macro_f1": 0.8755535151960584,
|
68 |
+
"eval_micro_f1": 0.8756143967020771,
|
69 |
+
"eval_runtime": 53.7192,
|
70 |
+
"eval_samples_per_second": 234.814,
|
71 |
+
"eval_steps_per_second": 14.687,
|
72 |
+
"step": 3680
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.17,
|
76 |
+
"learning_rate": 1.5657608695652177e-05,
|
77 |
+
"loss": 0.2369,
|
78 |
+
"step": 4000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 2.45,
|
82 |
+
"learning_rate": 1.511413043478261e-05,
|
83 |
+
"loss": 0.2101,
|
84 |
+
"step": 4500
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 2.72,
|
88 |
+
"learning_rate": 1.4570652173913045e-05,
|
89 |
+
"loss": 0.2086,
|
90 |
+
"step": 5000
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 2.99,
|
94 |
+
"learning_rate": 1.402717391304348e-05,
|
95 |
+
"loss": 0.2054,
|
96 |
+
"step": 5500
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 3.0,
|
100 |
+
"eval_accuracy": 0.8752972887268115,
|
101 |
+
"eval_loss": 0.2643134295940399,
|
102 |
+
"eval_macro_f1": 0.8747081066407124,
|
103 |
+
"eval_micro_f1": 0.8752972887268115,
|
104 |
+
"eval_runtime": 53.4868,
|
105 |
+
"eval_samples_per_second": 235.834,
|
106 |
+
"eval_steps_per_second": 14.751,
|
107 |
+
"step": 5520
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 3.26,
|
111 |
+
"learning_rate": 1.3483695652173915e-05,
|
112 |
+
"loss": 0.1676,
|
113 |
+
"step": 6000
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 3.53,
|
117 |
+
"learning_rate": 1.2940217391304348e-05,
|
118 |
+
"loss": 0.166,
|
119 |
+
"step": 6500
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 3.8,
|
123 |
+
"learning_rate": 1.2396739130434783e-05,
|
124 |
+
"loss": 0.1687,
|
125 |
+
"step": 7000
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 4.0,
|
129 |
+
"eval_accuracy": 0.8905977485333756,
|
130 |
+
"eval_loss": 0.2898699641227722,
|
131 |
+
"eval_macro_f1": 0.8905713282411306,
|
132 |
+
"eval_micro_f1": 0.8905977485333756,
|
133 |
+
"eval_runtime": 53.2546,
|
134 |
+
"eval_samples_per_second": 236.862,
|
135 |
+
"eval_steps_per_second": 14.816,
|
136 |
+
"step": 7360
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 4.08,
|
140 |
+
"learning_rate": 1.1853260869565217e-05,
|
141 |
+
"loss": 0.1576,
|
142 |
+
"step": 7500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 4.35,
|
146 |
+
"learning_rate": 1.1309782608695654e-05,
|
147 |
+
"loss": 0.1337,
|
148 |
+
"step": 8000
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 4.62,
|
152 |
+
"learning_rate": 1.0766304347826089e-05,
|
153 |
+
"loss": 0.132,
|
154 |
+
"step": 8500
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 4.89,
|
158 |
+
"learning_rate": 1.0223913043478262e-05,
|
159 |
+
"loss": 0.1362,
|
160 |
+
"step": 9000
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 5.0,
|
164 |
+
"eval_accuracy": 0.8894085936261297,
|
165 |
+
"eval_loss": 0.31742656230926514,
|
166 |
+
"eval_macro_f1": 0.8893640862987704,
|
167 |
+
"eval_micro_f1": 0.8894085936261297,
|
168 |
+
"eval_runtime": 53.5229,
|
169 |
+
"eval_samples_per_second": 235.675,
|
170 |
+
"eval_steps_per_second": 14.741,
|
171 |
+
"step": 9200
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 5.16,
|
175 |
+
"learning_rate": 9.680434782608696e-06,
|
176 |
+
"loss": 0.1243,
|
177 |
+
"step": 9500
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 5.43,
|
181 |
+
"learning_rate": 9.136956521739131e-06,
|
182 |
+
"loss": 0.1091,
|
183 |
+
"step": 10000
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 5.71,
|
187 |
+
"learning_rate": 8.593478260869566e-06,
|
188 |
+
"loss": 0.1092,
|
189 |
+
"step": 10500
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 5.98,
|
193 |
+
"learning_rate": 8.050000000000001e-06,
|
194 |
+
"loss": 0.1094,
|
195 |
+
"step": 11000
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 6.0,
|
199 |
+
"eval_accuracy": 0.8942444902489297,
|
200 |
+
"eval_loss": 0.36500877141952515,
|
201 |
+
"eval_macro_f1": 0.8942443599760673,
|
202 |
+
"eval_micro_f1": 0.8942444902489296,
|
203 |
+
"eval_runtime": 53.6838,
|
204 |
+
"eval_samples_per_second": 234.969,
|
205 |
+
"eval_steps_per_second": 14.697,
|
206 |
+
"step": 11040
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 6.25,
|
210 |
+
"learning_rate": 7.5076086956521745e-06,
|
211 |
+
"loss": 0.0934,
|
212 |
+
"step": 11500
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 6.52,
|
216 |
+
"learning_rate": 6.9641304347826085e-06,
|
217 |
+
"loss": 0.087,
|
218 |
+
"step": 12000
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 6.79,
|
222 |
+
"learning_rate": 6.420652173913044e-06,
|
223 |
+
"loss": 0.0921,
|
224 |
+
"step": 12500
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 7.0,
|
228 |
+
"eval_accuracy": 0.8950372601870937,
|
229 |
+
"eval_loss": 0.3785378932952881,
|
230 |
+
"eval_macro_f1": 0.8949877111068857,
|
231 |
+
"eval_micro_f1": 0.8950372601870938,
|
232 |
+
"eval_runtime": 52.9409,
|
233 |
+
"eval_samples_per_second": 238.266,
|
234 |
+
"eval_steps_per_second": 14.903,
|
235 |
+
"step": 12880
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 7.07,
|
239 |
+
"learning_rate": 5.877173913043479e-06,
|
240 |
+
"loss": 0.0833,
|
241 |
+
"step": 13000
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 7.34,
|
245 |
+
"learning_rate": 5.333695652173914e-06,
|
246 |
+
"loss": 0.073,
|
247 |
+
"step": 13500
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 7.61,
|
251 |
+
"learning_rate": 4.790217391304348e-06,
|
252 |
+
"loss": 0.0758,
|
253 |
+
"step": 14000
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 7.88,
|
257 |
+
"learning_rate": 4.246739130434783e-06,
|
258 |
+
"loss": 0.077,
|
259 |
+
"step": 14500
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 8.0,
|
263 |
+
"eval_accuracy": 0.8950372601870937,
|
264 |
+
"eval_loss": 0.48974281549453735,
|
265 |
+
"eval_macro_f1": 0.8950314309820686,
|
266 |
+
"eval_micro_f1": 0.8950372601870938,
|
267 |
+
"eval_runtime": 52.5947,
|
268 |
+
"eval_samples_per_second": 239.834,
|
269 |
+
"eval_steps_per_second": 15.001,
|
270 |
+
"step": 14720
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 8.15,
|
274 |
+
"learning_rate": 3.704347826086957e-06,
|
275 |
+
"loss": 0.0666,
|
276 |
+
"step": 15000
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 8.42,
|
280 |
+
"learning_rate": 3.1608695652173916e-06,
|
281 |
+
"loss": 0.0588,
|
282 |
+
"step": 15500
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 8.7,
|
286 |
+
"learning_rate": 2.617391304347826e-06,
|
287 |
+
"loss": 0.061,
|
288 |
+
"step": 16000
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 8.97,
|
292 |
+
"learning_rate": 2.0739130434782612e-06,
|
293 |
+
"loss": 0.059,
|
294 |
+
"step": 16500
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 9.0,
|
298 |
+
"eval_accuracy": 0.8965435230696052,
|
299 |
+
"eval_loss": 0.5619444847106934,
|
300 |
+
"eval_macro_f1": 0.8965343146604436,
|
301 |
+
"eval_micro_f1": 0.8965435230696052,
|
302 |
+
"eval_runtime": 52.94,
|
303 |
+
"eval_samples_per_second": 238.27,
|
304 |
+
"eval_steps_per_second": 14.904,
|
305 |
+
"step": 16560
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 9.24,
|
309 |
+
"learning_rate": 1.5304347826086956e-06,
|
310 |
+
"loss": 0.052,
|
311 |
+
"step": 17000
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 9.51,
|
315 |
+
"learning_rate": 9.869565217391304e-07,
|
316 |
+
"loss": 0.0495,
|
317 |
+
"step": 17500
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 9.78,
|
321 |
+
"learning_rate": 4.445652173913044e-07,
|
322 |
+
"loss": 0.0467,
|
323 |
+
"step": 18000
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 10.0,
|
327 |
+
"eval_accuracy": 0.8951165371809101,
|
328 |
+
"eval_loss": 0.6173644065856934,
|
329 |
+
"eval_macro_f1": 0.8951162464835035,
|
330 |
+
"eval_micro_f1": 0.8951165371809101,
|
331 |
+
"eval_runtime": 53.4503,
|
332 |
+
"eval_samples_per_second": 235.995,
|
333 |
+
"eval_steps_per_second": 14.761,
|
334 |
+
"step": 18400
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 10.0,
|
338 |
+
"step": 18400,
|
339 |
+
"total_flos": 1.548750605165568e+17,
|
340 |
+
"train_loss": 0.148325269014939,
|
341 |
+
"train_runtime": 6107.1251,
|
342 |
+
"train_samples_per_second": 96.384,
|
343 |
+
"train_steps_per_second": 3.013
|
344 |
+
}
|
345 |
+
],
|
346 |
+
"max_steps": 18400,
|
347 |
+
"num_train_epochs": 10,
|
348 |
+
"total_flos": 1.548750605165568e+17,
|
349 |
+
"trial_name": null,
|
350 |
+
"trial_params": null
|
351 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3701bd14ba501856b7f7615489551d876fa61df9c631ee7cc0e9bde4f1aec059
|
3 |
+
size 3579
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|